Probabilistic Counterexample Guidance for Safer Reinforcement Learning (Extended Version).
Xiaotong JiAntonio FilieriPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- probabilistic model
- function approximation
- generative model
- learning problems
- model free
- posterior probability
- markov decision processes
- data driven
- state space
- bayesian networks
- probability theory
- machine learning
- optimal policy
- action selection
- probabilistic reasoning
- probabilistic logic
- function approximators
- autonomous learning
- context sensitive
- information theoretic
- database
- dynamic programming
- multi agent
- artificial intelligence
- learning algorithm
- neural network
- data sets